NVIDIA Triton Inference Server

Model serving with Triton Inference Server

Out of date

This guide contains outdated information pertaining to Kubeflow 1.0. This guide needs to be updated for Kubeflow 1.1.

Kubeflow currently doesn’t have a specific guide for NVIDIA Triton Inference Server. Note that Triton was previously known as the TensorRT Inference Server. See the NVIDIA documentation for instructions on running NVIDIA inference server on Kubernetes.

Last modified 21.04.2021: Components v external add ons (#2630) (42f08be0)